Also, OCR of printed Bangla texts has been extensively studied. Some studies on extraction of Bangla texts from scene images are available in the literature. We tested our algorithm on a repository of 100 scene images containing texts of Devanagari and / or Bangla Moreover, we studied the problem of binarization of such scene images and observed that there are situations when repeated binarization by a well-known global thresholding approach is effective. Additionally, we consider a few criteria for robust filtering of text components from such scene images. A common unique feature of these two scripts is the presence of headline and the proposed scheme uses mathematical morphology operations for their extraction. ![]() In this article, we propose a novel and effective scheme based on analysis of connected components for extraction of Devanagari and Bangla texts from camera captured scene images. The extracted text can be sent to OCR or to a text-to-speech engine for recognition. ![]() One such problem is extraction of texts from natural scene images captured by such devices. With the increasing popularity of digital cameras attached with various handheld devices, many new computational challenges have gained significance.
0 Comments
Leave a Reply. |